End of training
Browse files
README.md
CHANGED
|
@@ -15,8 +15,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
# llama_tune_01
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [Bllossom/llama-3.2-Korean-Bllossom-3B](https://huggingface.co/Bllossom/llama-3.2-Korean-Bllossom-3B) on an unknown dataset.
|
| 18 |
-
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 3.9284
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -41,16 +39,10 @@ The following hyperparameters were used during training:
|
|
| 41 |
- seed: 42
|
| 42 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 43 |
- lr_scheduler_type: linear
|
| 44 |
-
- lr_scheduler_warmup_steps: 5
|
| 45 |
- num_epochs: 3
|
| 46 |
|
| 47 |
### Training results
|
| 48 |
|
| 49 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
-
|:-------------:|:-----:|:----:|:---------------:|
|
| 51 |
-
| 4.32 | 1.0 | 25 | 4.1997 |
|
| 52 |
-
| 3.8543 | 2.0 | 50 | 3.9833 |
|
| 53 |
-
| 3.8308 | 3.0 | 75 | 3.9284 |
|
| 54 |
|
| 55 |
|
| 56 |
### Framework versions
|
|
|
|
| 15 |
# llama_tune_01
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [Bllossom/llama-3.2-Korean-Bllossom-3B](https://huggingface.co/Bllossom/llama-3.2-Korean-Bllossom-3B) on an unknown dataset.
|
|
|
|
|
|
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
|
|
| 39 |
- seed: 42
|
| 40 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 41 |
- lr_scheduler_type: linear
|
|
|
|
| 42 |
- num_epochs: 3
|
| 43 |
|
| 44 |
### Training results
|
| 45 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
|
| 47 |
|
| 48 |
### Framework versions
|